Method and device for calculating focus position of urine sediment detector, equipment and medium

Abstract

The application discloses a kind of urinary sediment detector focal position calculation method, device, equipment and medium, the method is by obtaining the respective corresponding laminar flow image of multiple image acquisition positions, and determine the multiple particle images of multiple laminar flow images respectively;Respectively in the multiple particle images of multiple laminar flow images respectively, determine the target particle image corresponding to multiple laminar flow images respectively;According to the number of target particle image, determine Gaussian function curve, and determine focal position based on Gaussian function curve.The method of the application can avoid the failure of focal position calculation due to the same clarity value of multiple laminar flow images when calculating the focal position of laminar flow.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and in particular relates to a method, device, equipment and medium for calculating the focal position of a urine sediment detector. Background Technology

[0002] With the rapid development of science and technology, image processing technology has received increasing attention and importance, and has been widely used in various industries.

[0003] Currently, a smooth curve is calculated based on interpolation for all laminar flow images captured. The horizontal axis of the curve corresponds to the image sequence ID, and the vertical axis corresponds to the image sharpness. The image with the highest sharpness value on the curve is then regarded as the laminar flow image captured at the focal point, and the focal point is determined based on the image ID. However, since the laminar flow in the urine sediment detector has a certain thickness, particles may fluctuate within the laminar flow. This can lead to the simultaneous presence of particles in front of, above, and behind the focal point in the same laminar flow image. Consequently, multiple laminar flow images may have the same sharpness value, resulting in multiple maxima on the final calculated smooth curve. It is impossible to determine which maxima is the true focal point.

[0004] In summary, how to avoid the failure of focal position calculation due to the same sharpness value of multiple laminar flow images when calculating the focal position has become an urgent technical problem to be solved in the field of image processing technology. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and medium for calculating the focal position of a urine sediment detector. This aims to avoid the failure to calculate the focal position of laminar flow due to multiple laminar flow images having the same sharpness value.

[0006] To achieve the above objectives, the present invention provides a method for calculating the focal position of a urine sediment detector, the method comprising:

[0007] Acquire laminar flow images corresponding to each of the multiple image acquisition locations, and determine multiple particle images for each of the multiple laminar flow images;

[0008] In each of the multiple particle images of the multiple laminar flow images, a target particle image corresponding to each of the multiple laminar flow images is determined;

[0009] The Gaussian function curve is determined based on the number of target particle images, and the focal position is determined based on the Gaussian function curve.

[0010] Optionally, the step of determining the target particle image corresponding to each of the plurality of laminar flow images in the plurality of particle images of each of the plurality of laminar flow images includes:

[0011] Each of the multiple laminar flow images is processed by an algorithm to obtain the category corresponding to each of the multiple particle images;

[0012] The particle images categorized as being at the front end of the focus and close to the focus are identified as the first target particle images corresponding to each of the multiple laminar flow maps;

[0013] The particle images categorized as being located behind and near the focal point are identified as the second target particle images corresponding to each of the multiple laminar flow maps.

[0014] Optionally, the step of determining the Gaussian function curve based on the number of target particles in the image, and determining the focal position based on the Gaussian function curve, includes:

[0015] The first Gaussian function curve is determined based on the number of first target particle images corresponding to each of the multiple laminar flow images;

[0016] The second Gaussian function curve is determined based on the number of second target particle images corresponding to each of the multiple laminar flow images;

[0017] The focal point is determined based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

[0018] Optionally, the step of determining the first Gaussian function curve based on the number of first target particle images corresponding to each of the plurality of laminar flow images includes:

[0019] A first data point set is determined based on the number of the first target particle images corresponding to each of the multiple laminar flow images;

[0020] Gaussian function curve fitting is performed on the first data point set to obtain the first Gaussian function curve;

[0021] The step of determining the second Gaussian function curve based on the number of second target particle images corresponding to each of the multiple laminar flow images includes:

[0022] The second data point set is determined based on the number of the second target particle images corresponding to each of the multiple laminar flow images;

[0023] Gaussian function curve fitting is performed on the second data point set to obtain the second Gaussian function curve.

[0024] Optionally, the step of determining the focal position based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve includes:

[0025] Determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determine the target laminar flow image among the multiple laminar flow images based on the target intersection point;

[0026] The focal position is determined based on the image acquisition position corresponding to the target laminar flow image.

[0027] Optionally, the step of determining the target intersection point between the first Gaussian function curve and the second Gaussian function curve includes:

[0028] Based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve, the target intersection point between the first Gaussian function curve and the second Gaussian function curve is determined.

[0029] Optionally, the step of determining the plurality of particle images for each of the plurality of laminar flow images includes:

[0030] Each of the laminar flow images is segmented to obtain multiple particle images for each of the laminar flow images.

[0031] Furthermore, to achieve the above objectives, the present invention also provides a focal position calculation device for a urine sediment detector, the focal position calculation device comprising:

[0032] The particle image module acquires laminar flow images corresponding to multiple image acquisition locations and determines multiple particle images for each of the multiple laminar flow images;

[0033] The target particle image module determines the target particle image corresponding to each of the multiple laminar flow images from the multiple particle images of each of the multiple laminar flow images;

[0034] The focus position module determines the Gaussian function curve based on the number of target particle images, and determines the focus position based on the Gaussian function curve.

[0035] In addition, to achieve the above objectives, the present invention also provides a terminal device, the terminal device comprising: a memory, a processor, and a urine sediment detector focal position calculation program stored in the memory and executable on the processor, wherein when the urine sediment detector focal position calculation program of the terminal device is executed by the processor, it implements the steps of the urine sediment detector focal position calculation method as described above.

[0036] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a urine sediment detector focal position calculation program, which, when executed by a processor, implements the steps of the urine sediment detector focal position calculation method as described above.

[0037] This invention provides a method, apparatus, terminal device, and computer-readable storage medium for calculating the focal position of a urine sediment detector. The method involves acquiring laminar flow images corresponding to multiple image acquisition locations and determining multiple particle images corresponding to each of the multiple laminar flow images; determining target particle images corresponding to each of the multiple particle images of the multiple laminar flow images; determining a Gaussian function curve based on the number of target particle images; and determining the focal position based on the Gaussian function curve.

[0038] This invention acquires laminar flow images from multiple image acquisition locations using a urine sediment detector. Multiple particle images are identified within each of these laminar flow images. Then, target particle images are identified within each of the multiple particle images in each laminar flow image. A Gaussian function curve is determined based on the number of target particle images in each laminar flow image. Finally, the focal point where the laminar flow can be focused and imaged is determined based on this Gaussian function curve. This invention avoids the situation where the focal point calculation fails due to multiple laminar flow images having the same sharpness value. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the device structure of the terminal device hardware operating environment involved in the embodiments of the present invention;

[0040] Figure 2 This is a flowchart illustrating the steps of the first embodiment of the method for calculating the focal position of the urine sediment detector of the present invention.

[0041] Figure 3 This is a schematic diagram of the number distribution of the second and fourth types of particles and the Gaussian function curve fitting results involved in an embodiment of the focal position calculation method of the urine sediment detector of the present invention.

[0042] Figure 4 This is a schematic diagram of various types of particle images involved in an embodiment of the focal position calculation method of the urine sediment detector of the present invention;

[0043] Figure 5 This is a schematic diagram of the functional modules of a focal position calculation device for a urine sediment detector according to an embodiment of the present invention.

[0044] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0046] Reference Figure 1 , Figure 1 This is a schematic diagram of the hardware operating environment of the terminal device involved in the embodiment of the present invention.

[0047] The terminal device in this embodiment of the invention can be a terminal device applied in the field of image processing technology. Specifically, the terminal device in this embodiment of the invention is a urine sediment detector.

[0048] like Figure 1 As shown, the terminal device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1 The terminal device structure shown does not constitute a limitation on the terminal device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a focus position calculation program for a urine sediment detector.

[0051] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate data with it; user interface 1003 is mainly used to connect to the client and communicate data with it; and processor 1001 can be used to call the urine sediment detector focus position calculation program stored in memory 1005 and perform the following operations:

[0052] Acquire laminar flow images corresponding to each of the multiple image acquisition locations, and determine multiple particle images for each of the multiple laminar flow images;

[0053] In each of the multiple particle images of the multiple laminar flow images, a target particle image corresponding to each of the multiple laminar flow images is determined;

[0054] The Gaussian function curve is determined based on the number of target particle images, and the focal position is determined based on the Gaussian function curve.

[0055] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0056] Each of the multiple laminar flow images is processed by an algorithm to obtain the category corresponding to each of the multiple particle images;

[0057] The particle images categorized as being at the front end of the focus and close to the focus are identified as the first target particle images corresponding to each of the multiple laminar flow maps;

[0058] The particle images categorized as being located behind and near the focal point are identified as the second target particle images corresponding to each of the multiple laminar flow maps.

[0059] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0060] The first Gaussian function curve is determined based on the number of first target particle images corresponding to each of the multiple laminar flow images;

[0061] The second Gaussian function curve is determined based on the number of second target particle images corresponding to each of the multiple laminar flow images;

[0062] The focal point is determined based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

[0063] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0064] A first data point set is determined based on the number of the first target particle images corresponding to each of the multiple laminar flow images;

[0065] Gaussian function curve fitting is performed on the first data point set to obtain the first Gaussian function curve;

[0066] The second data point set is determined based on the number of the second target particle images corresponding to each of the multiple laminar flow images;

[0067] Gaussian function curve fitting is performed on the second data point set to obtain the second Gaussian function curve.

[0068] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0069] Determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determine the target laminar flow image among the multiple laminar flow images based on the target intersection point;

[0070] The focal position is determined based on the image acquisition position corresponding to the target laminar flow image.

[0071] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0072] Based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve, the target intersection point between the first Gaussian function curve and the second Gaussian function curve is determined.

[0073] Optionally, the processor 1001 can also be used to call the urine sediment detector focal position calculation program stored in the memory 1005 and perform the following operations:

[0074] Each of the laminar flow images is segmented to obtain multiple particle images for each of the laminar flow images.

[0075] Based on the aforementioned terminal equipment, various embodiments of the method for calculating the focal position of the urine sediment detector of the present invention are proposed.

[0076] Currently, a smooth curve is calculated based on interpolation for all laminar flow images captured. The horizontal axis of the curve corresponds to the image sequence ID, and the vertical axis corresponds to the image sharpness. The image with the highest sharpness value on the curve is then regarded as the laminar flow image captured at the focal point, and the focal point is determined based on the image ID. However, since the laminar flow in the urine sediment detector has a certain thickness, particles may fluctuate within the laminar flow. This can lead to the simultaneous presence of particles in front of, above, and behind the focal point in the same laminar flow image, resulting in multiple laminar flow images having the same sharpness value. Consequently, the final calculated smooth curve has multiple maxima, making it impossible to determine which maxima is the true focal point.

[0077] To address the aforementioned issues, this invention proposes a method for calculating the focal position of a urine sediment detector. The method involves acquiring laminar flow images from multiple image acquisition locations, identifying multiple particle images within each laminar flow image, and then identifying target particle images corresponding to each of these particle images. A Gaussian function curve is determined based on the number of target particle images in each laminar flow image. Finally, the focal position where the laminar flow can be focused and imaged is determined based on this Gaussian function curve. This invention avoids the scenario where the focal position calculation fails due to multiple laminar flow images having the same sharpness value.

[0078] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the focal position calculation method for the urine sediment detector of the present invention. It should be noted that although the logical order is shown in the flowchart, in certain situations, the focal position calculation method for the urine sediment detector of the present invention may, of course, execute the steps shown or described in a different order than that shown here.

[0079] In a first embodiment of the method for calculating the focal position of the urine sediment detector of the present invention, the method includes:

[0080] Step S10: Obtain laminar flow images corresponding to each of the multiple image acquisition locations, and determine multiple particle images for each of the multiple laminar flow images;

[0081] In this embodiment, the urine sediment detector acquires laminar flow images collected at multiple image acquisition locations and determines multiple particle images corresponding to each of the multiple laminar flow images.

[0082] For example, the laminar flow is captured by the camera of the urine sediment detector at different locations to obtain 500 laminar flow images, and then the particle images in each laminar flow image are determined.

[0083] Furthermore, in a feasible embodiment, the method for calculating the focal position of the urine sediment detector of the present invention, in step S10 above, the step of "determining multiple particle images of each of the multiple laminar flow images" may include:

[0084] Step S101: Perform image segmentation processing on the multiple laminar flow images to obtain multiple particle images for each of the multiple laminar flow images.

[0085] In this embodiment, the urine sediment detector performs image segmentation processing on multiple laminar flow images to obtain multiple particle images corresponding to each of the multiple flow images.

[0086] For example, the urine sediment detector performs image segmentation processing on 500 laminar flow images. Assuming that 10 particle components are captured in one of the 500 laminar flow images, then this laminar flow image is segmented into 10 particle images.

[0087] It should be noted that the urine sediment detector draws a certain amount of sample and injects it into a flat flow cell using a syringe, forming a laminar flow. The liquid in the laminar flow carries particles at high speed, so the number of particles varies randomly in the laminar flow images captured by the camera of the urine sediment detector at different positions.

[0088] Step S20: In each of the multiple particle images of the multiple laminar flow images, determine the target particle image corresponding to each of the multiple laminar flow images;

[0089] In this embodiment, the urine sediment detector determines the target particle image corresponding to each of the multiple laminar flow images from the multiple particle images corresponding to each of the multiple laminar flow images.

[0090] For example, a urine sediment detector identifies a target particle image among multiple particle images corresponding to each of 500 laminar flow images.

[0091] Step S30: Determine the Gaussian function curve based on the number of target particle images, and determine the focal position based on the Gaussian function curve.

[0092] In this embodiment, the urine sediment detector determines the Gaussian function curve based on the number of target particle images in the multiple particle images corresponding to each laminar flow image, and determines the focal position where the laminar flow is clearly focused and imaged based on the Gaussian function curve.

[0093] In this embodiment, the focal position calculation method of the urine sediment detector of the present invention acquires laminar flow images at multiple image acquisition positions using the urine sediment detector, and performs image segmentation processing on the multiple laminar flow images to obtain multiple particle images corresponding to each of the multiple laminar flow images; the urine sediment detector determines the target particle image corresponding to each of the multiple laminar flow images in the multiple particle images corresponding to each of the multiple laminar flow images; the urine sediment detector determines a Gaussian function curve based on the number of target particle images in the multiple particle images corresponding to each laminar flow image, and determines the focal position where the laminar flow is clearly focused and imaged based on the Gaussian function curve.

[0094] Thus, this embodiment of the invention acquires laminar flow images from multiple image acquisition locations using a urine sediment detector, determines multiple particle images corresponding to each of the multiple laminar flow images, then determines the target particle images among the multiple particle images corresponding to each of the multiple laminar flow images, and determines a Gaussian function curve based on the number of target particle images in each laminar flow image. Finally, based on the Gaussian function curve, the focal point position where the laminar flow can be focused and imaged is determined. In this way, the present invention avoids the situation where the focal point position calculation fails due to multiple laminar flow images having the same sharpness value.

[0095] Furthermore, based on the first embodiment of the method for calculating the focal position of the urine sediment detector of the present invention, a second embodiment of the method for calculating the focal position of the urine sediment detector of the present invention is proposed.

[0096] In this embodiment, the method for calculating the focal position of the urine sediment detector of the present invention, step S20 above may include:

[0097] Step S201: Perform algorithm processing on the multiple particle images of each of the multiple laminar flow images to obtain the category corresponding to each of the multiple particle images;

[0098] Step S202: The particle images classified as being at the front end of the focal point and close to the focal point are determined as the first target particle images corresponding to each of the multiple laminar flow maps;

[0099] Step S203: The particle images classified as being behind and near the focal point are determined as the second target particle images corresponding to each of the multiple laminar flow maps.

[0100] In this embodiment, the urine sediment detector performs algorithmic processing on multiple particle images to calculate the category corresponding to each of the multiple particle images. Then, the particle image with the category of being at the front end of the focal point and close to the focal point is determined as the first target particle image corresponding to each of the multiple laminar flow images, and the particle image with the category of being at the rear end of the focal point and close to the focal point is determined as the second target particle image corresponding to each of the multiple laminar flow images.

[0101] It should be noted that the category of the front of the focus that is close to the focus point is category 2, and the category of the back of the focus that is close to the focus point is category 3.

[0102] For example, such as Figure 4As shown, the particle image is classified into five categories: Category 1, Category 2, Category 3, Category 4, and Category 5. Category 1 indicates that the particle image is located at the front of the focal point, far from the focal point; Category 2 indicates that the particle image is located at the front of the focal point, relatively close to the focal point; Category 3 indicates that the particle image is located near the focal point; Category 4 indicates that the particle image is located at the rear of the focal point, relatively close to the focal point; and Category 5 indicates that the particle image is located at the rear of the focal point, far from the focal point. Therefore, the category of the particle image can be determined based on its shape and blur information.

[0103] For example, the urine sediment detector adjusts multiple particle images to a uniform size and then inputs them into a pre-trained convolutional neural network. The convolutional neural network outputs the corresponding category for each particle image based on its morphological and blur information. Since particle images of categories 1 and 5 are far from the focal point and have little value in calculating the focal point, they are not considered. Particle images of category 3 are near the focal point; however, laminar flow images taken at this location may also contain particles before and after the focal point, potentially misleading the calculation of the focal point position, so they are also not considered. Here, only the distribution of particles of categories 2 and 4 in the 500 laminar flow images is considered. Therefore, particle images of category 2 are the first target particle images, and particle images of category 4 are the second target particle images.

[0104] Furthermore, in a feasible embodiment, step S30 above may include:

[0105] Step S301: Determine the first Gaussian function curve based on the number of first target particle images corresponding to each of the multiple laminar flow images;

[0106] In this embodiment, the urine sediment detector determines the first Gaussian function curve corresponding to the first target particle image based on the number of first target particle images in the multiple particle images corresponding to each of the multiple laminar flow images.

[0107] For example, the urine sediment detector determines the first target particle image among all particle images corresponding to all laminar flow images. Specifically, it determines all the first target particle images from 5000 particle images corresponding to 500 laminar flow images acquired at different acquisition locations, and then determines the quantity distribution of the first target particle image in each laminar flow image, thereby determining the Gaussian function curve corresponding to the first target particle image.

[0108] Step S302: Determine the second Gaussian function curve based on the number of second target particle images corresponding to each of the multiple laminar flow images;

[0109] In this embodiment, the urine sediment detector determines the second Gaussian function curve corresponding to the second target particle image based on the number of second target particle images in the multiple particle images corresponding to each of the multiple laminar flow images.

[0110] For example, the urine sediment detector determines the second target particle image among all particle images corresponding to all laminar flow images. Specifically, it determines all the second target particle images from 5000 particle images corresponding to 500 laminar flow images acquired at different acquisition locations, and then determines the quantity distribution of the second target particle image in each laminar flow image, thereby determining the Gaussian function curve corresponding to the second target particle image.

[0111] Step S303: Determine the focal position based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

[0112] In this embodiment, the urine sediment detector obtains the target intersection point between the first Gaussian function curve corresponding to the first target particle image and the second Gaussian function curve corresponding to the second target particle image, and determines the focal position of the laminar flow to be clearly focused and imaged based on the target intersection point.

[0113] It should be noted that the above focal position refers to the shooting position of the urine sediment detector camera corresponding to the laminar flow image captured when the laminar flow is successfully focused.

[0114] For example, a first Gaussian curve is obtained based on the quantity distribution of the first target particle image in 500 laminar flow images, and a second Gaussian curve is obtained based on the quantity distribution of the second target particle image in 500 laminar flow images. There are at most two intersection points between the two Gaussian curves. The target intersection point between the two Gaussian function curves is determined, and the focal position is determined based on the position of the target intersection point on the curve.

[0115] Furthermore, in a feasible embodiment, step S301 above may include:

[0116] Step A: Determine the first data point set based on the number of the first target particle images corresponding to each of the multiple laminar flow images;

[0117] Step B: Fit a Gaussian function curve to the first data point set to obtain the first Gaussian function curve;

[0118] In this embodiment, the urine sediment detector determines the first data point set based on the number of first target particle images in the multiple particle images corresponding to each of the multiple laminar flow images, and then performs Gaussian function curve fitting processing on the first data point set to obtain the first Gaussian function curve corresponding to the first target particle image.

[0119] For example, such as Figure 3 As shown, the analysis results of 500 laminar flow images captured during a real focusing process are presented. The particle number distribution of category 2 represents the distribution of the particle image number of category 2 in the 500 laminar flow images. The first Gaussian function curve is obtained by fitting the number distribution with a Gaussian function.

[0120] It should be noted that each of the multiple laminar flow images acquired by the camera of the urine sediment detector corresponds to an ID. Specifically, if 500 laminar flow images are acquired, the ID of the first acquired laminar flow image is 1, and the ID of the 500th acquired laminar flow image is 500.

[0121] For example, assuming the number of category 2 particles in the i-th laminar flow image is ki, then after analyzing 500 laminar flow images, a quantity distribution vector v1 = [k1, k2, ..., k500] can be obtained, where each element in the vector is normalized to obtain the normalized vector v1 norm, as follows:

[0122]

[0123] Where sum(v1) represents the summation of elements in vector v1. Based on the id of the laminar flow image, assuming the position vector p = [1, 2, ..., 500], the mean and standard deviation of the Gaussian function are:

[0124]

[0125]

[0126] The equation of the first Gaussian function curve is:

[0127]

[0128] Where y1 represents the probability density and x represents the image ID.

[0129] Furthermore, in a feasible embodiment, step S302 above may include:

[0130] Step C: Determine the second data point set based on the number of the second target particle images corresponding to each of the multiple laminar flow images;

[0131] Step D: Fit a Gaussian function curve to the second data point set to obtain a second Gaussian function curve.

[0132] In this embodiment, the urine sediment detector determines the second data point set based on the number of second target particle images in the multiple particle images corresponding to each of the multiple laminar flow images. Then, it performs Gaussian function curve fitting processing on the second data point set to obtain the second Gaussian function curve corresponding to the second target particle image.

[0133] For example, such as Figure 3 As shown, the particle number distribution of category 4 represents the distribution of the particle image number of category 4 in 500 laminar flow images. Gaussian function fitting is performed on this number distribution to obtain the second Gaussian function curve.

[0134] For example, assuming the number of category 2 particles in the i-th laminar flow image is Ti, then after analyzing 500 laminar flow images, a quantity distribution vector v2 = [T1, T2, ..., T500] can be obtained, where each element in the vector is normalized to obtain the normalized vector v2norm, as follows:

[0135]

[0136] Here, sum(v2) represents the summation of the elements in vector v2. Based on the id of the laminar flow image, assuming the position vector p = [1, 2, ..., 500], the mean and standard deviation of the Gaussian function are:

[0137]

[0138]

[0139] The equation of the second Gaussian function curve is:

[0140]

[0141] Where y2 represents the probability density and x represents the image ID.

[0142] In this embodiment, the focal position calculation method of the urine sediment detector of the present invention performs algorithmic processing on multiple particle images by the urine sediment detector to calculate the category corresponding to each of the multiple particle images. Then, the particle image with the category of being at the front of the focal point and close to the focal point is determined as the first target particle image corresponding to each of the multiple laminar flow images, and the particle image with the category of being at the rear of the focal point and close to the focal point is determined as the second target particle image corresponding to each of the multiple laminar flow images. The urine sediment detector determines a first data point set based on the number of first target particle images in the multiple particle images corresponding to each of the multiple laminar flow images, and then applies a Gaussian function to the first data point set. Curve fitting is performed to obtain the first Gaussian function curve corresponding to the first target particle image. The urine sediment detector determines the second data point set based on the number of second target particle images in the multiple particle images corresponding to each of the multiple laminar flow images. Then, Gaussian function curve fitting is performed on the second data point set to obtain the second Gaussian function curve corresponding to the second target particle image. Based on the first Gaussian function curve corresponding to the first target particle image and the second Gaussian function curve corresponding to the second target particle image, the urine sediment detector obtains the target intersection point between the first Gaussian function curve and the second Gaussian function curve. The focal point position of the laminar flow being clearly focused and imaged is determined based on the target intersection point.

[0143] Thus, based on the qualitative judgment of the image sharpness of multiple particle images, the particle number distribution of category 2 and category 4 is reasonably selected to obtain the first Gaussian function curve corresponding to the particle image of category 2 and the second Gaussian function curve corresponding to the particle image of category 4, which facilitates the subsequent calculation of the focal position based on the two Gaussian function curves.

[0144] Furthermore, based on the first and / or second embodiments of the method for calculating the focal position of the urine sediment detector of the present invention, a third embodiment of the method for calculating the focal position of the urine sediment detector of the present invention is proposed.

[0145] In this embodiment, the method for calculating the focal position of the urine sediment detector of the present invention, step S303 above may include:

[0146] Step E: Determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determine the target laminar flow image among the multiple laminar flow images based on the target intersection point;

[0147] Step F: Determine the focal position based on the image acquisition position corresponding to the target laminar flow image.

[0148] In this embodiment, the urine sediment detector determines the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determines the target laminar flow image among multiple laminar flow images corresponding to the target intersection point based on the obtained target intersection point. Then, it determines the focal position based on the image acquisition position corresponding to the target laminar flow image.

[0149] For example, the urine sediment detector finds the abscissa corresponding to the target intersection point between the first Gaussian function curve and the second Gaussian function curve, which is the ID of the target laminar flow image. Based on the ID, the image acquisition position of the target laminar flow image is determined. The image acquisition position is the focal position of the camera of the urine sediment detector when the laminar flow can be successfully focused and imaged.

[0150] It should be noted that the ID of the laminar flow image above corresponds to the physical location of the camera of the urine sediment detector.

[0151] Furthermore, in a feasible embodiment, step E above, the step of "determining the target intersection point between the first Gaussian function curve and the second Gaussian function curve" may include:

[0152] Step E01: Based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve, determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

[0153] In this embodiment, the urine sediment detector determines the target intersection point between the first Gaussian function curve and the second Gaussian function curve based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve.

[0154] For example, the equation for calculating the intersection point of two Gaussian function curves is as follows:

[0155]

[0156] Theoretically, the equation has at most two solutions, meaning the two Gaussian function curves have at most two intersection points. Since there can only be one intersection point between the two means, the solution between μ1 and μ2 is taken as the target intersection point.

[0157] In this embodiment, the focal position calculation method of the urine sediment detector of the present invention determines the target intersection point between the first Gaussian function curve and the second Gaussian function curve based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve. Then, based on the obtained target intersection point, the target laminar flow image is determined among multiple laminar flow images corresponding to the target intersection point. Finally, the focal position is determined based on the image acquisition position corresponding to the target laminar flow image.

[0158] Thus, by taking the laminar flow image with the intersection point of the two Gaussian function curves as the focal point, the influence of multiple extreme points on the focal point calculation in existing technologies is avoided in principle. Theoretically, only one possible focal point can be calculated at most.

[0159] In addition, embodiments of the present invention also provide a focal position calculation device for a urine sediment detector.

[0160] Please refer to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the focal position calculation device of the urine sediment detector of the present invention, as shown below. Figure 5 As shown, the focal position calculation device of the urine sediment detector of the present invention includes:

[0161] The particle image module 10 is used to acquire laminar flow images corresponding to multiple image acquisition locations, and to determine multiple particle images for each of the multiple laminar flow images;

[0162] The target particle image module 20 is used to determine the target particle image corresponding to each of the multiple laminar flow images in the multiple particle images of each of the multiple laminar flow images;

[0163] The focus position module 30 is used to determine the Gaussian function curve based on the number of target particles in the image, and to determine the focus position based on the Gaussian function curve.

[0164] Optionally, the target particle image module 20 includes:

[0165] The category unit is used to perform algorithmic processing on the multiple particle images of each of the multiple laminar flow images to obtain the category corresponding to each of the multiple particle images;

[0166] The first target particle image unit is used to determine the particle images classified as being at the front end of the focal point and close to the focal point as the first target particle images corresponding to each of the multiple laminar flow maps.

[0167] The second target particle image unit is used to determine the particle images categorized as being behind and near the focal point as the second target particle images corresponding to each of the multiple laminar flow maps.

[0168] Optionally, the focus position module 30 includes:

[0169] The first Gaussian function curve unit is used to determine the first Gaussian function curve based on the number of first target particle images corresponding to each of the multiple laminar flow images;

[0170] The second Gaussian function curve unit is used to determine the second Gaussian function curve based on the number of second target particle images corresponding to each of the multiple laminar flow images;

[0171] The focal position unit is used to determine the focal position based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

[0172] Optionally, the first Gaussian function curve unit is further configured to determine a first data point set based on the number of the first target particle images corresponding to each of the plurality of laminar flow images; and to perform Gaussian function curve fitting on the first data point set to obtain a first Gaussian function curve; the second Gaussian function curve unit is further configured to determine a second data point set based on the number of the second target particle images corresponding to each of the plurality of laminar flow images; and to perform Gaussian function curve fitting on the second data point set to obtain a second Gaussian function curve.

[0173] Optionally, the focus position unit is further configured to determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determine the target laminar flow image among the multiple laminar flow images based on the target intersection point; and determine the focus position based on the image acquisition position corresponding to the target laminar flow image.

[0174] Optionally, the focus position unit is further configured to determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve.

[0175] Optionally, the particle image module 10 is further configured to perform image segmentation processing on the multiple laminar flow images respectively to obtain multiple particle images for each of the multiple laminar flow images.

[0176] The present invention also provides a computer storage medium storing a focal position calculation program for a urine sediment detector, wherein when the focal position calculation program for a urine sediment detector is executed by a processor, the program implements the steps of the focal position calculation program method for a urine sediment detector as described in any of the above embodiments.

[0177] The specific embodiments of the computer storage medium of the present invention are basically the same as the embodiments of the focal position calculation program method of the urine sediment detector of the present invention described above, and will not be repeated here.

[0178] The present invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the method for calculating the focal position of the urine sediment detector as described in any of the above embodiments, which will not be elaborated here.

[0179] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0180] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0181] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (such as TWS earphones, etc.) to execute the methods described in the various embodiments of the present invention.

[0182] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for calculating the focal position of a urine sediment detector, characterized in that, The method for calculating the focal position of the urine sediment detector includes: Acquire laminar flow images corresponding to each of the multiple image acquisition locations, and determine multiple particle images for each of the multiple laminar flow images; In each of the multiple particle images of the multiple laminar flow images, a target particle image corresponding to each of the multiple laminar flow images is determined; The Gaussian function curve is determined based on the number of target particles in the image, and the focal position is determined based on the Gaussian function curve. The step of determining the target particle image corresponding to each of the multiple laminar flow images in the multiple particle images of each of the multiple laminar flow images includes: Each of the multiple laminar flow images is processed by an algorithm to obtain the category corresponding to each of the multiple particle images; The particle images categorized as being at the front end of the focal plane and close to the focal plane are determined as the first target particle images corresponding to each of the multiple laminar flow images; The particle images categorized as being located behind and near the focal point are identified as the second target particle images corresponding to each of the multiple laminar flow images; The step of determining the Gaussian function curve based on the number of target particles in the image, and determining the focal position based on the Gaussian function curve, includes: The first Gaussian function curve is determined based on the number of first target particle images corresponding to each of the multiple laminar flow images; The second Gaussian function curve is determined based on the number of second target particle images corresponding to each of the multiple laminar flow images; The focal point is determined based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

2. The method for calculating the focal position of a urine sediment detector as described in claim 1, characterized in that, The step of determining the first Gaussian function curve based on the number of first target particle images corresponding to each of the multiple laminar flow images includes: A first data point set is determined based on the number of the first target particle images corresponding to each of the multiple laminar flow images; Gaussian function curve fitting is performed on the first data point set to obtain the first Gaussian function curve; The step of determining the second Gaussian function curve based on the number of second target particle images corresponding to each of the multiple laminar flow images includes: The second data point set is determined based on the number of the second target particle images corresponding to each of the multiple laminar flow images; Gaussian function curve fitting is performed on the second data point set to obtain the second Gaussian function curve.

3. The method for calculating the focal position of a urine sediment detector as described in claim 1, characterized in that, The step of determining the focal position based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve includes: Determine the target intersection point between the first Gaussian function curve and the second Gaussian function curve, and determine the target laminar flow image among the multiple laminar flow images based on the target intersection point; The focal position is determined based on the image acquisition position corresponding to the target laminar flow image.

4. The method for calculating the focal position of a urine sediment detector as described in claim 3, characterized in that, The step of determining the target intersection point between the first Gaussian function curve and the second Gaussian function curve includes: Based on the mean of the first Gaussian function curve and the mean of the second Gaussian function curve, the target intersection point between the first Gaussian function curve and the second Gaussian function curve is determined.

5. The method for calculating the focal position of a urine sediment detector as described in claim 1, characterized in that, The step of determining multiple particle images for each of the multiple laminar flow images includes: Each of the laminar flow images is segmented to obtain multiple particle images for each of the laminar flow images.

6. A focal position calculation device for a urine sediment detector, characterized in that, The focal position calculation device of the urine sediment detector includes: The particle image module acquires laminar flow images corresponding to multiple image acquisition locations and determines multiple particle images for each of the multiple laminar flow images; The target particle image module determines the target particle image corresponding to each of the multiple laminar flow images from the multiple particle images of each of the multiple laminar flow images; The focus position module determines a Gaussian function curve based on the number of target particles in the image, and determines the focus position based on the Gaussian function curve. The target particle image module is further configured to perform algorithmic processing on the multiple particle images of each of the multiple laminar flow images to obtain the category corresponding to each of the multiple particle images; The particle images categorized as being at the front end of the focal plane and close to the focal plane are determined as the first target particle images corresponding to each of the multiple laminar flow images; The particle images categorized as being located behind and near the focal point are identified as the second target particle images corresponding to each of the multiple laminar flow images; The focus position module is also used to determine the first Gaussian function curve based on the number of first target particle images corresponding to each of the multiple laminar flow images; The second Gaussian function curve is determined based on the number of second target particle images corresponding to each of the multiple laminar flow images; The focal point is determined based on the target intersection point between the first Gaussian function curve and the second Gaussian function curve.

7. A terminal device, characterized in that, The terminal device includes: a memory, a processor, and a urine sediment detector focal position calculation program stored in the memory and executable on the processor. When the urine sediment detector focal position calculation program is executed by the processor, it implements the steps of the urine sediment detector focal position calculation method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a focal position calculation program for a urine sediment detector, which, when executed by a processor, implements the steps of the focal position calculation method for a urine sediment detector as described in any one of claims 1 to 5.

Images